Neural CRF transducers for sequence labeling
This work addresses sequence labeling problems for NLP researchers and practitioners, offering incremental improvements over existing methods.
The paper tackled sequence labeling tasks like POS tagging, chunking, and NER by proposing NCRF transducers, which improved over linear-chain NCRFs and RNN transducers across all evaluated tasks and achieved state-of-the-art results.
Conditional random fields (CRFs) have been shown to be one of the most successful approaches to sequence labeling. Various linear-chain neural CRFs (NCRFs) are developed to implement the non-linear node potentials in CRFs, but still keeping the linear-chain hidden structure. In this paper, we propose NCRF transducers, which consists of two RNNs, one extracting features from observations and the other capturing (theoretically infinite) long-range dependencies between labels. Different sequence labeling methods are evaluated over POS tagging, chunking and NER (English, Dutch). Experiment results show that NCRF transducers achieve consistent improvements over linear-chain NCRFs and RNN transducers across all the four tasks, and can improve state-of-the-art results.